Some requirements: everything in success criteria should be able to make it come true. better have user interface because there is someone son’t know computer that much there should be at least 10 terms in test plan
8 examples: resizing : It is an effective resizing of images that not only use geometric constraints but consider the image content as well. Propose a simple image operator seam-carving: can change the size of an image by gracefully carving-out or in-setting pixel in different parts of the image website: __http://www.win.tue.nl/~wstahw/edu/2IV05/__
deblur : Despite its usefulness to human viewers, motion is often the bane of photography: the clearest, most detailed digital photo requires a perfectly stationary camera and a motionless scene. Relative motion causes motion blur in the photo. Current practice presumes a 0th order model of motion; it seeks the longest possible exposure time for which moving objects will still appear motionless. Our goal is to address a first-order motion model: movements with constant speed rather than constant position. Ideally, the camera would enable us to obtain a sharp, detailed record of each moving component of an image, plus its movement. website: http://web.media.mit.edu/~raskar/deblur/CodedExpousreLowres.pdf
dehazing
Images of outdoor scenes are usually degraded by the turbid medium (e.g., particles, water-droplets) in the atmosphere.Haze removal1 (or dehazing) is highly desired in both consumer/computational photography and computer vision applications. First, removing haze can significantly increase the visibility of the scene and correct the color shift caused by the airlight. Second, most computer vision algorithms, from low-level image analysis to high-level object recognition, usually assume that the input image (after radiometric calibration) is the scene radiance.e. Last, the haze removal can produce depth information and benefit many vision algorithms and advanced image editing. website: __http://research.microsoft.com/en-us/um/people/jiansun/papers/Dehaze_CVPR2009.pdf__
HDR Two concepts: exposure: how bright is the scene overall. Dynamic range: contrast in the scene High dynamic range (HDR) is a dynamic range higher than what is considered to be standard dynamic range. The term is often used in discussing displays, photography, 3D rendering, and sound recording including digital imaging and digital audio production. The term may apply to an analog or digitized signal, or to the means of recording, processing, and reproducing such signals. website: __http://groups.csail.mit.edu/graphics/classes/CompPhoto06/html/lecturenotes/08_HDR_6.pdf__
segmentation An image segmentation problem can be interpreted as partitioning the image elements (pixels/voxels) into different categories.A Cut of a graph is a partition of the vertices in the graph into two disjoint subsets.Constructing a graph with an image, we can solve the segmentation problem using techniques for graph cuts in graph theory website : __http://www.coe.utah.edu/~cs7640/readings/graph_cuts_intro.pdf__
inpainting when we want to restoring old pictures when it got strokes back.The basic idea is simple: Replace those bad marks with its neighbouring pixels so that it looks like the neigbourhood.Several algorithms were designed for this purpose and OpenCV provides two of them. website : __http://docs.opencv.org/master/df/d3d/tutorial_py_inpainting.html__
everything in success criteria should be able to make it come true.
better have user interface because there is someone son’t know computer that much
there should be at least 10 terms in test plan
8 examples:
resizing : It is an effective resizing of images that not only use geometric constraints but consider the image content as well. Propose a simple image operator seam-carving: can change the size of an image by gracefully carving-out or in-setting pixel in different parts of the image
website: __http://www.win.tue.nl/~wstahw/edu/2IV05/__
deblur :
Despite its usefulness to human viewers, motion is often the bane of photography: the clearest, most detailed digital photo requires a perfectly stationary camera and a motionless scene. Relative motion causes motion blur in the photo. Current practice presumes a 0th order model of motion; it seeks the longest possible exposure time for which moving objects will still appear motionless. Our goal is to address a first-order motion model: movements with constant speed rather than constant position. Ideally, the camera would enable us to obtain a sharp, detailed record of each moving component of an image, plus its movement.
website: http://web.media.mit.edu/~raskar/deblur/CodedExpousreLowres.pdf
dehazing
Images of outdoor scenes are usually degraded by the turbid medium (e.g., particles, water-droplets) in the atmosphere.Haze removal1 (or dehazing) is highly desired in both consumer/computational photography and computer vision applications. First, removing haze can significantly increase the visibility of the scene and correct the color shift caused by the airlight. Second, most computer vision algorithms, from low-level image analysis to high-level object recognition, usually assume that the input image (after radiometric calibration) is the scene radiance.e. Last, the haze removal can produce depth information and benefit many vision algorithms and advanced image editing.
website: __http://research.microsoft.com/en-us/um/people/jiansun/papers/Dehaze_CVPR2009.pdf__
HDR
Two concepts: exposure: how bright is the scene overall. Dynamic range: contrast in the scene
High dynamic range (HDR) is a dynamic range higher than what is considered to be standard dynamic range. The term is often used in discussing displays, photography, 3D rendering, and sound recording including digital imaging and digital audio production. The term may apply to an analog or digitized signal, or to the means of recording, processing, and reproducing such signals.
website: __http://groups.csail.mit.edu/graphics/classes/CompPhoto06/html/lecturenotes/08_HDR_6.pdf__
segmentation
An image segmentation problem can be interpreted as partitioning the image elements (pixels/voxels) into different categories.A Cut of a graph is a partition of the vertices in the graph into two disjoint subsets.Constructing a graph with an image, we can solve the segmentation problem using techniques for graph cuts in graph theory
website : __http://www.coe.utah.edu/~cs7640/readings/graph_cuts_intro.pdf__
inpainting
when we want to restoring old pictures when it got strokes back.The basic idea is simple: Replace those bad marks with its neighbouring pixels so that it looks like the neigbourhood.Several algorithms were designed for this purpose and OpenCV provides two of them.
website : __http://docs.opencv.org/master/df/d3d/tutorial_py_inpainting.html__
stylization
It is the transferring the style from one image onto another can be considered a problem of texture transfer. In texture transfer the goal is to synthesize a texture from a source image while constraining the texture synthesis in order to preserve the semantic content of a target image.
website: __http://www.cv-foundation.org/openaccess/content_cvpr_2016/papers/Gatys_Image_Style_Transfer_CVPR_2016_paper.pdf__
face recognition
can be use for check of attendance
website : __http://brightguo.com/face-recognition-with-opencv/__